Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations only declare read-only/idempotent/open-world; the description adds materially more: typical latency 0.3-2 s, price USD 0.005 per call, a free tier of 3 searches per IP per UTC day, and an explicit prompt-injection warning to treat results as untrusted data. These are exactly the operational facts an agent needs before spending money.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Purpose is front-loaded, followed by sibling routing, then cost/latency/quota, then the safety caveat. Every sentence carries distinct information; nothing is repeated from the title or schema.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

An output schema exists, so return values need no prose explanation, and the description still covers pricing, quota, latency, and trust posture. Nothing an agent needs in order to invoke this correctly is missing.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, with count, query, country, and freshness all documented including ranges and examples. The description adds no parameter-level meaning beyond the schema, so the baseline 3 applies; 'ranked results (title, url, snippet)' describes output, not inputs.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb and resource (search the web for a query), the exact return shape (ranked title, url, snippet), and the underlying index (Mojeek), which distinguishes it from a generic aggregator. An agent can tell it apart from search_with_contents and news_search without opening any schema.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Names two explicit alternatives with the condition that selects each: search_with_contents when page text is needed in the same call, news_search for news. No exclusions are left to inference.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.